Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging

Abstract

Many methods applied to data acquired by various imaging modalities have been evaluated for their benefit in localizing lesions in magnetic resonance (MR) negative epilepsy patients. No approach has proven to be a stand‐alone method with sufficiently high sensitivity and specificity. The presented study addresses the potential benefit of the automated fusion of results of individual methods in presurgical evaluation. We collected electrophysiological, MR, and nuclear imaging data from 137 patients with pharmacoresistant MR‐negative/inconclusive focal epilepsy. A subgroup of 32 patients underwent surgical treatment with known postsurgical outcomes and histopathology. We employed a Gaussian mixture model to reveal several classes of gray matter tissue. Classes specific to epileptogenic tissue were identified and validated using the surgery subgroup divided into two disjoint sets. We evaluated the classification accuracy of the proposed method at a voxel‐wise level and assessed the effect of individual methods. The training of the classifier resulted in six classes of gray matter tissue. We found a subset of two classes specific to tissue located in resected areas. The average classification accuracy (i.e., the probability of correct classification) was significantly higher than the level of chance in the training group (0.73) and even better in the validation surgery subgroup (0.82). Nuclear imaging, diffusion‐weighted imaging, and source localization of interictal epileptic discharges were the strongest methods for classification accuracy. We showed that the automatic fusion of results can identify brain areas that show epileptogenic gray matter tissue features. The method might enhance the presurgical evaluations of MR‐negative epilepsy patients.

Multimodal combination of neuroimaging methods for localizing the epileptogenic zone in MR-negative epilepsy

“…In terms of imaging development, the IMs used in this study are composed of traditional as well as recently introduced methods. Traditional methods include well-established methods such as FDG-PET and SISCOM 30 – 32 . The clinical utility of these methods has been proven.…”

Epileptogenic zone detection in MRI negative epilepsy using adaptive thresholding of arterial spin labeling data

“…We showed that this method is suitable for use in clinical environments. AI indexes computed from ASL data appear to be helpful in EZ localization in MRI-negative epilepsy, especially in combination with other methods from the standard clinical presurgical protocol 11 .…”

“…ASL has been proven to be useful in EZ localization in this type of epilepsy 3 , 10 . ASL plays an important role in EZ localization in combination with other methods 11 . In this work, we focus on processing ASL independently of other methods suitable for EZ detection; we intend to present ASL as one of the methods important for reaching a final decision on EZ localization in MRI-negative epilepsy.…”

The benefit of the diffusion kurtosis imaging in presurgical evaluation in patients with focal MR-negative epilepsy

“…Improving the detection of brain areas responsible for epileptic seizure generation in patients that do not respond to pharmacotherapy and lack macroscopic structural abnormalities at the same time is a challenging topic that many researchers are trying to resolve. Due to an advancement in computational possibilities, a growing number of studies fuse multimodal data in order to achieve more accurate results through complex analytical approaches 41 , 42 . The detection rate of such advanced computational algorithms of course strongly depends on the accuracy of each method that enters the multimodal fusion.…”